Structure-aware World Model for Probe Guidance via Large-scale Self-supervised Pre-train

TL;DR

This paper introduces a large-scale self-supervised pre-training approach to develop a cardiac structure-aware world model, improving echocardiography probe guidance by understanding heart structures and spatial relationships.

Contribution

It presents a novel self-supervised task for structural inference in echocardiography and leverages over 1.36 million images for large-scale pre-training to enhance probe guidance accuracy.

Findings

Pre-trained model reduces guidance errors across standard views.

Structure-aware pre-training benefits clinical echocardiography scanning.

Model trained on 1.36 million echocardiograms demonstrates improved spatial understanding.

Abstract

The complex structure of the heart leads to significant challenges in echocardiography, especially in acquisition cardiac ultrasound images. Successful echocardiography requires a thorough understanding of the structures on the two-dimensional plane and the spatial relationships between planes in three-dimensional space. In this paper, we innovatively propose a large-scale self-supervised pre-training method to acquire a cardiac structure-aware world model. The core innovation lies in constructing a self-supervised task that requires structural inference by predicting masked structures on a 2D plane and imagining another plane based on pose transformation in 3D space. To support large-scale pre-training, we collected over 1.36 million echocardiograms from ten standard views, along with their 3D spatial poses. In the downstream probe guidance task, we demonstrate that our pre-trained model consistently reduces guidance errors across the ten most common standard views on the test set with 0.29 million samples from 74 routine clinical scans, indicating that structure-aware pre-training benefits the scanning.